Add streamlit filter and make some lint adjustments

src/streamlit_app.py

@@ -1,6 +1,7 @@
 import os
 import streamlit as st
 import pandas as pd
+from streamlit_filter import filter_dataframe
 
 
 LEAGUE_NAME = "LOFG"
@@ -32,8 +33,8 @@ def get_app():
         "eligible",
     ]
 
-    st.subheader("Raw data")
-    st.write(data[raw_display_columns])
+    filtered_data = filter_dataframe(data[raw_display_columns])
+    st.write(filtered_data)
 
 
 if __name__ == "__main__":

src/streamlit_filter.py

@@ -0,0 +1,87 @@
+# https://blog.streamlit.io/auto-generate-a-dataframe-filtering-ui-in-streamlit-with-filter_dataframe/
+
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,
+)
+import pandas as pd
+import streamlit as st
+
+
+def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Adds a UI on top of a dataframe to let viewers filter columns
+
+    Args:
+        df (pd.DataFrame): Original dataframe
+
+    Returns:
+        pd.DataFrame: Filtered dataframe
+    """
+    modify = st.checkbox("Add filters")
+
+    if not modify:
+        return df
+
+    df = df.copy()
+
+    # Try to convert datetimes into a standard format (datetime, no timezone)
+    for col in df.columns:
+        if is_object_dtype(df[col]):
+            try:
+                df[col] = pd.to_datetime(df[col])
+            except Exception:
+                pass
+
+        if is_datetime64_any_dtype(df[col]):
+            df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        to_filter_columns = st.multiselect("Filter dataframe on", df.columns)
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            # Treat columns with < 17 unique values as categorical
+            if is_categorical_dtype(df[column]) or df[column].nunique() < 17:
+                user_cat_input = right.multiselect(
+                    f"Values for {column}",
+                    df[column].unique(),
+                    default=list(df[column].unique()),
+                )
+                df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Values for {column}",
+                    min_value=_min,
+                    max_value=_max,
+                    value=(_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            elif is_datetime64_any_dtype(df[column]):
+                user_date_input = right.date_input(
+                    f"Values for {column}",
+                    value=(
+                        df[column].min(),
+                        df[column].max(),
+                    ),
+                )
+                if isinstance(user_date_input, tuple):
+                    if len(user_date_input) == 2:
+                        user_date_input_dt = tuple(map(pd.to_datetime, user_date_input))
+                        start_date, end_date = user_date_input_dt
+                        df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                user_text_input = right.text_input(
+                    f"Substring or regex in {column}",
+                )
+                if user_text_input:
+                    df = df[df[column].astype(str).str.contains(user_text_input)]
+
+    return df